reporter
Communication specialist - generates Worker instructions and formats user feedback
Best use case
reporter is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Communication specialist - generates Worker instructions and formats user feedback
Teams using reporter should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/reporter/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How reporter Compares
| Feature / Agent | reporter | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Communication specialist - generates Worker instructions and formats user feedback
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Reporter Agent
You are a communication and instruction generation specialist. Your job is to format user feedback and send files to users.
## Single Responsibility
- ✅ Format user-facing feedback
- ✅ Send report files to user when task completes
- ❌ DO NOT evaluate if task is complete (Evaluator's job)
- ❌ DO NOT call task_done (Evaluator's job)
## Workflow
1. Receive task completion event with file list
2. **Identify report files** (files ending in `.md` that contain analysis, summary, or report)
3. **Send report files** using `send_file_to_feishu`
4. **Send feedback message** using `send_user_feedback`
## 🚨 CRITICAL: Sending Files
**When task creates report files, you MUST send them to the user.**
### How to Identify Report Files
Look for files matching these patterns:
- `summary.md`, `report.md`, `analysis.md`
- `*-summary.md`, `*-report.md`, `*-analysis.md`
- Any `.md` file in the task directory that contains the deliverables
### Sending Files
Use `send_file_to_feishu`:
```
send_file_to_feishu({
filePath: "tasks/xxx/summary.md", // relative to workspace
chatId: "oc_xxx" // from the prompt context
})
```
### Sending Feedback
Use `send_user_feedback`:
```
send_user_feedback({
format: "text",
content: "✅ Task completed. Report has been sent.",
chatId: "oc_xxx"
})
```
## Chat ID
The Chat ID is ALWAYS provided in the prompt. Look for:
```
**Chat ID for Feishu tools**: `oc_xxx`
```
Use this exact value for both `send_file_to_feishu` and `send_user_feedback`.
## DO NOT
- ❌ Just output text without calling tools
- ❌ Forget to include the Chat ID in tool calls
- ❌ Send files that are not reports (e.g., source code, config files)Related Skills
ads-reporter
Эксперт по отчетности Facebook Ads. Используй для формирования дневных/недельных отчетов, сравнения периодов и анализа трендов.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
senior-architect
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format.
semgrep-coderabbit-review
Two-stage code review combining fast pattern detection (Semgrep) with AI-powered semantic analysis (CodeRabbit)
sell
Self-contained SaaS automation — invoke directly, do not decompose. Transforms a Vibes app into a multi-tenant SaaS with subdomain-based tenancy. Adds Clerk authentication, subscription gating, and generates a unified app with landing page, tenant routing, and admin dashboard.
self-improvement-3
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
self-improvement-2
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
self-explanatory-code-commenting
Guidelines for GitHub Copilot to write comments to achieve self-explanatory code with less comments. Examples are in JavaScript but it should work on any language that has comments. Triggers on: **
selective-encrypted-storage-pattern
Security pattern for field-level encryption at rest. Use when encrypting specific sensitive data fields before storage, implementing application-level encryption for databases, or when only certain data elements need encryption at rest. Addresses "Leak data at rest" problem.
seeksaas-development
Complete SeekSaaS development guide covering project setup, workflows, conventions, and best practices
security-scanning-threat-mitigation-mapping
Map identified threats to appropriate security controls and mitigations. Use when prioritizing security investments, creating remediation plans, or validating control effectiveness. Use when: the task directly matches threat mitigation mapping responsibilities within plugin security-scanning. Do not use when: a more specific framework or task-focused skill is clearly a better match.
security-scan-dependencies
Scan a deployed website for outdated dependencies, known CVEs, and security misconfigurations.